+ All Categories
Home > Documents > Main Work Kk

Main Work Kk

Date post: 02-Jun-2018
Category:
Upload: chika-albert
View: 224 times
Download: 0 times
Share this document with a friend

of 36

Transcript
  • 8/10/2019 Main Work Kk

    1/36

    Page 1of 36

    CHAPTER ONE

    1.0 INTRODUCTION

    Timely identification of newly emerging trends is very important to businesses. Sales patterns of

    customer segments indicate market trends. Upward and downward trends in sales signify new

    market trends. Time-seriespredictive modeling can be used to identify market trends embedded

    in changes of sales revenues.

    Predictive analytics encompasses a variety of techniques fromstatistics,modeling,machine

    learning, anddata mining that analyze current and historical facts to makepredictions about

    future, or otherwise unknown, events.

    In business, predictive models exploitpatterns found in historical and transactional data to

    identify risks and opportunities. Models capture relationships among many factors to allow

    assessment of risk or potential associated with a particular set of conditions, guidingdecisionmaking for candidate transactions.

    Predictive analytics is used inactuarial science,marketingfinancial

    services,insurance,telecommunications,retail,

    travel, healthcare,pharmaceuticals and other

    fields.

    One of the most well known applications iscredit scoring,which is used throughoutfinancial

    services. Scoring models process a customer's credit history, loan application, customer data,

    etc., in order to rank-order individuals by their likelihood of making future credit payments on

    time

    Predictive models analyze past performance to assess how likely a customer is to exhibit a

    specific behavior in order to improvemarketing effectiveness.This category also encompasses

    models that seek out subtle data patterns to answer questions about customer performance, such

    as fraud detection models. Predictive models often perform calculations during live transactions,

    for example, to evaluate the risk or opportunity of a given customer or transaction, in order to

    guide a decision. With advancements in computing speed, individual agent modeling systems

    have become capable of simulating human behaviors or reactions to given stimuli or scenarios.

    The new term for animating data specifically linked to an individual in a simulated environment

    is avatar analytics

    Understanding of sales trends is important for marketing as well as for customer retention.

    Regression is an analytic technique used in developing predictive models for numerical data. It

    automatically derives mathematical functions that summarize trends embedded in past historical

    data, in such a way that minimizes the errors between actual input data and predicted values by

    the models. Regression can be applied to time-series data. A time-series consists of a set of

    observations which are measured at specific time intervals, say, monthly, quarterly, yearly, etc.

    Observations we are interested are sales revenues.

    http://www.roselladb.com/predictive-modeling.htmhttp://en.wikipedia.org/wiki/Statisticshttp://en.wikipedia.org/wiki/Predictive_modellinghttp://en.wikipedia.org/wiki/Machine_learninghttp://en.wikipedia.org/wiki/Machine_learninghttp://en.wikipedia.org/wiki/Data_mininghttp://en.wikipedia.org/wiki/Predictionhttp://en.wikipedia.org/wiki/Pattern_detectionhttp://en.wikipedia.org/wiki/Decision_makinghttp://en.wikipedia.org/wiki/Decision_makinghttp://en.wikipedia.org/wiki/Actuarial_sciencehttp://en.wikipedia.org/wiki/Marketinghttp://en.wikipedia.org/wiki/Financial_serviceshttp://en.wikipedia.org/wiki/Financial_serviceshttp://en.wikipedia.org/wiki/Insurancehttp://en.wikipedia.org/wiki/Telecommunicationshttp://en.wikipedia.org/wiki/Retailhttp://en.wikipedia.org/wiki/Travelhttp://en.wikipedia.org/wiki/Healthcarehttp://en.wikipedia.org/wiki/Pharmaceutical_companyhttp://en.wikipedia.org/wiki/Credit_scoringhttp://en.wikipedia.org/wiki/Financial_serviceshttp://en.wikipedia.org/wiki/Financial_serviceshttp://en.wikipedia.org/wiki/Credit_historyhttp://en.wikipedia.org/wiki/Loan_applicationhttp://en.wikipedia.org/wiki/Marketing_effectivenesshttp://en.wikipedia.org/wiki/Marketing_effectivenesshttp://en.wikipedia.org/wiki/Loan_applicationhttp://en.wikipedia.org/wiki/Credit_historyhttp://en.wikipedia.org/wiki/Financial_serviceshttp://en.wikipedia.org/wiki/Financial_serviceshttp://en.wikipedia.org/wiki/Credit_scoringhttp://en.wikipedia.org/wiki/Pharmaceutical_companyhttp://en.wikipedia.org/wiki/Healthcarehttp://en.wikipedia.org/wiki/Travelhttp://en.wikipedia.org/wiki/Retailhttp://en.wikipedia.org/wiki/Telecommunicationshttp://en.wikipedia.org/wiki/Insurancehttp://en.wikipedia.org/wiki/Financial_serviceshttp://en.wikipedia.org/wiki/Financial_serviceshttp://en.wikipedia.org/wiki/Marketinghttp://en.wikipedia.org/wiki/Actuarial_sciencehttp://en.wikipedia.org/wiki/Decision_makinghttp://en.wikipedia.org/wiki/Decision_makinghttp://en.wikipedia.org/wiki/Pattern_detectionhttp://en.wikipedia.org/wiki/Predictionhttp://en.wikipedia.org/wiki/Data_mininghttp://en.wikipedia.org/wiki/Machine_learninghttp://en.wikipedia.org/wiki/Machine_learninghttp://en.wikipedia.org/wiki/Predictive_modellinghttp://en.wikipedia.org/wiki/Statisticshttp://www.roselladb.com/predictive-modeling.htm
  • 8/10/2019 Main Work Kk

    2/36

    Page 2of 36

    The analytical technique used for this research is the time series model. It is used for predicting

    or forecasting the future behavior of variables. These models account for the fact that data points

    taken over time may have an internal structure (such as autocorrelation, trend or seasonal

    variation) that should be accounted for. As a result standard regression techniques cannot be

    applied to time series data and methodology has been developed to decompose the trend,

    seasonal and cyclical component of the series. Modeling the dynamic path of a variable can

    improve forecasts since the predictable component of the series can be projected into the future.

    Time series models estimate difference equations containing stochastic components. Two

    commonly used forms of these models are autoregressive models (AR) andmoving

    average (MA) models. TheBox-Jenkins methodology (1976) developed by George Box and

    G.M. Jenkins combines the AR and MA models to produce the ARMA (autoregressive moving

    average) model which is the cornerstone of stationary time series analysis.ARIMA

    (autoregressive integrated moving average models) on the other hand are used to describe non-

    stationary time series. Box and Jenkins suggest differencing a non stationary time series to obtain

    a stationary series to which an ARMA model can be applied. Non stationary time series have apronounced trend and do not have a constant long-run mean or variance.

    Box and Jenkins proposed a three stage methodology which includes: model identification,

    estimation and validation. The identification stage involves identifying if the series is stationary

    or not and the presence of seasonality by examining plots of the series, autocorrelation and

    partial autocorrelation functions. In the estimation stage, models are estimated using non-linear

    time series or maximum likelihood estimation procedures. Finally the validation stage involves

    diagnostic checking such as plotting the residuals to detect outliers and evidence of model fit.

    Nyce, Charles (2007),Predictive Analytics White Paper, American Institute for Chartered

    Property Casualty Underwriters/Insurance Institute of America.

    1.2 SCOPE AND LIMITATION

    1.2.1 SCOPE

    NBC operates the Apapa Plant since 1958 and is located in the Apapa area of Lagos State inSouth-West Nigeria. The Apapa plant is responsible for the production of Coca-Cola, Fanta,

    Sprite and Schweppes and distribution of all product categories. Coca-Cola was an instant hit

    with the Nigerian consumer and has remained so. Over the next six decades, NBC has continued

    on its journey keeping its promise of refreshing consumers, strengthening its communities,

    enriching the workplace and preserving the environment while recording many memorable

    milestones along the way.

    http://en.wikipedia.org/wiki/Autoregressive_modelhttp://en.wikipedia.org/wiki/Moving_average_modelhttp://en.wikipedia.org/wiki/Moving_average_modelhttp://en.wikipedia.org/wiki/Box-Jenkinshttp://en.wikipedia.org/wiki/Autoregressive_moving_average_modelhttp://en.wikipedia.org/wiki/Autoregressive_integrated_moving_averagehttp://www.aicpcu.org/doc/predictivemodelingwhitepaper.pdfhttp://www.aicpcu.org/doc/predictivemodelingwhitepaper.pdfhttp://www.aicpcu.org/doc/predictivemodelingwhitepaper.pdfhttp://www.aicpcu.org/doc/predictivemodelingwhitepaper.pdfhttp://en.wikipedia.org/wiki/Autoregressive_integrated_moving_averagehttp://en.wikipedia.org/wiki/Autoregressive_moving_average_modelhttp://en.wikipedia.org/wiki/Box-Jenkinshttp://en.wikipedia.org/wiki/Moving_average_modelhttp://en.wikipedia.org/wiki/Moving_average_modelhttp://en.wikipedia.org/wiki/Autoregressive_model
  • 8/10/2019 Main Work Kk

    3/36

    Page 3of 36

    1.2.2 LIMITATION

    The process of getting the data for this research was quite cumbersome, demanding but on the

    overall, its quite rewarding.

    1.3 OBJECTIVES of the Study

    1. To fit a model to the sales of each soft drink and forecast with it.

    2. To compare the sales performance of the soft drinks

    1.4 LITERATURE REVIEW

    Some of the greatest contributors to the theme of the study are:

    Christensen and Brogan (1971) in a journal on modeling and optimal control of a production

    process disclosed that an industrial production process is modeled as a discrete-time system with

    a disturbance input due to sales.. The state consists of rates of flow of parts or subassemblies at

    various work stations, backlogs of parts awaiting processing, and the inventory level of the

    finished product. The control variables are the man-hours scheduled for various work processes.

    A quadratic performance criterion is minimized so as to keep state and control variables near

    desired values. Dynamic programming is used and numerical examples are provided

    Mandal (1980) in an article on vendor selection using interpretive structural modeling wrote that

    Vendor selection is one of the most important activities of a purchasing department.

    Traditionally, vendors are selected for their ability to meet the quality requirement, delivery

    performance and the price offered. However, as they are selected not only to meet the immediate

    requirement but also future needs, one needs to consider many other factors when selecting a

    reliable vendor. Analyses some of the most important criteria which have been classified into

    four categories: autonomous, dependent, linkage and driver depending on their driver power and

    dependence. Develops an interpretive structural model (ISM) to show the inter-relationship of

    different criteria and their levels of importance in the vendor selection process. Reveals thatattitude and willingness for business and after sales service are as important factors as

    quality, delivery and practice. These criteria are dependent on all the others. This analysis could

    provide a meaningful analytical base in the vendor selection process.

    Betts et al (1996) in his article on Consumer behavior and the retail sales noted that In spite of

    the ubiquity of seasonal and other retail sales, they have been curiously neglected within the

  • 8/10/2019 Main Work Kk

    4/36

    Page 4of 36

    marketing literature. This is most surprising, given their impact on profit-margins, brand/store

    images, supplier-retailer relationships and consumer behavior. Since 1980, the effects of

    comparison price advertising on consumer behavior have received growing attention from

    researchers, although much of this literature has been at the individual product level and

    confined to groceries. Builds on this research in the specific context of store wide sales, where

    the impact of reductions extends far beyond the sum of individual price changes. Based on focus

    groups and preliminary surveys of sale shoppers, develops and tests a typology of motivations.

    Presents taxonomy of responses to sales, illustrating alternative behavioral responses.

    Concludes with a model of the attitude problem brought about by recession, overcapacity,

    overuse of the strategy and growing skepticism on the part of consumers.

    Simon et al (1999) in an article on modeling of the cycle of products with data acquisition

    features were of the opinion that Domestic appliances are long-lived and relatively expensive

    products that come under the new EC electrical waste recovery directive. In the UK, washing

    machines in particular tend to be unreliable; increasing the reuse of components could improve

    the economics of end-of-life operations. Trends in appliance design are towards more

    sophisticated control and networking; this makes adding functions to record data on the use of

    the machines feasible. The data would also have value for life cycle environmental assessment.

    The paper reports on the development of self-contained data acquisition units for washing

    machines based on a microcontroller and non-volatile memory. The data has applications in

    design, marketing and servicing as well as end-of-life. A batch of units have been manufactured

    and tested on limited field trials in washing machines. Ten parameters are continuously

    monitored, timed and/or recorded during appliance operation; error conditions are also logged

    for use during servicing. The data is then downloaded, either during servicing or at end-of-life;

    the dynamic data from use is combined with static data from manufacture. The information

    system which links all parties interested in the data is the key aspect of life cycle data

    acquisition. Two models are described which evaluate the economic benefits of adding such

    functions to products: a steady-state model as used by previous authors who were concerned with

    end-of-life product treatment and a more sophisticated transient model that accurately reflects the

    limited life of designs. Results show that in this case, more reusable components arise from

    servicing rather than from end-of-life recovery of parts. The cost savings from increased reuseare also estimated to be comparable to the additional cost of the system; greater savings could

    well arise from the use of the use data in marketing.

  • 8/10/2019 Main Work Kk

    5/36

    Page 5of 36

    Heyse and Wei (2005) in a book on modeling the advertising-sales relationship through use of

    multiple time series techniques were of the view that when time series data are available for both

    advertising and sales, it may be worthwhile to model the two series jointly. Such an analysis may

    contribute to our understanding of the dynamic relationships among the series and may improve

    the accuracy of forecasts. Multiple time series techniques are applied to the well-known Lydia

    Pinkham data to illustrate their use in modeling the advertising-sales relationship. In analyzing

    the Lydia Pinkham data the need for a joint model is established and a bivariate model is

    identified, estimated and checked. Its forecasting properties are discussed and compared to other

    time series approaches.

    Hoptroff (2005) in a journal on the principles and practice of time series forecasting and business

    modeling using neural nets used a hands-on practical discussion of how and why neural

    networks are used in forecasting and business modeling. The need for forecasting is briefly

    examined. The theory of the multilayer preceptor neural network is then covered both

    qualitatively and in mathematical detail, including the methods of back-propagation of error and

    independent validation. The advantages of the neural net approach to forecasting, namely

    nonlinear modeling capability, plausible interpolations and extrapolations, robustness to noise,

    ill-conditioning and insufficient data, and ease of use, are discussed. Finally, some working notes

    are offered for the practical implementation of neural nets in forecasting, and four real-life

    examples are given from the pursuits of econometrics, sales forecasting, market modelling, and

    risk evaluation.

    Gupta et al (2005) in a journal on differential sales tax structure noted that it contributes

    significantly to distribution network decisions that build logistics inefficiencies in firms

    operating in India. In this paper, we develop a model for determining distribution centers (DCs)

    locations considering the impact of CST. A non-linear mixed integer-programming problem that

    is formulated initially is approximated to a mixed integer-programming problem. Using a

    numeric example, the effect of CST rates and product variety on DC locations is studied and

    found to be having impact. It is felt that the Indian Government proposal to switch over from the

    present sales tax regime to value added tax (VAT) regime would significantly contribute to

    reducing the logistics inefficiencies of Indian firms.

    Burgess (2006) in a book on modeling business profitability noted that various methods are in

    use for the top down assessment and comparison of the future profitability of businesses. The

    most advanced is the PAR equation of the PIMS programme, which combines quantitative

    evaluations of the average effect of various business characteristics on profitability. However it

    is not a true model in the OR sense being essentially a linear regression equation. The proposed

    new approach is a first attempt to combine the characteristics in a way which models the

    bargaining of customers with suppliers who are in competition for the supply of a bulk product.

    All the constants in the resulting non-linear equation (called 5C) are meaningful in marketing or

    production terms. The model is in a preliminary non-optimized state, but seems to offer

    opportunities for ongoing development. It is in this spirit that it is offered for discussion.

  • 8/10/2019 Main Work Kk

    6/36

    Page 6of 36

    Buzzell and Wiersema (2006) in a journal on modeling changes in market share noted that the

    decision to build market share has major resource-allocation implications. To aid managers in

    assessing these implications, research was conducted to determine general relationships between

    changes in market share and variables representing market strategies and competitive position.

    The research was based on multiproduct, cross-sectional regression analyses and includes

    variables that are - or should be readily available to most businesses.

    Chanda and Bardhan (2008) in a book on modeling innovation wrote that Majority of consumer

    durables have multiple technological generations. Each succeeding generation offers some

    innovative performance enhancements, feature additions etc. distinguishing itself from the past

    releases. Therefore the consumer's attitude towards each of them can be very different. There is a

    need to understand consumer psychology and have accurate measure to predict the adoption

    process of new technology. Mathematical models have proved to be ideal tools to explain the

    past purchasing-behavior and also for forecasting. This paper focuses on studying the relative

    changes of diffusion parameters for both first time purchasers and upgraders along with

    developing a more general sales model for multiple technology generation products. The

    proposed model explicitly identifies different groups of purchaser viz. first timers and repeaters

    (upgraders).

    Themido et al (2006) in a journal on modeling the retail sale of gasoline described the modelling

    approach for the sales of gasoline in service stations located in a Portuguese metropolitan area.

    The models were developed for planning purposes in order to assess potential sales of new sites.

    The estimates produced are more accurate than those made by previous models and are currently

    being used to support investment decisions of the largest Portuguese company. Starting from a

    basic multiplicative regression model, several segmentations of the service stations were

    obtained. Among these, the sub-models for service stations located in urban areas and for service

    stations located along routes produced a better fit. The models reflect, without exception, the

    importance of the variables representing the size of service station and the traffic passing by,

    as well as variables which express location and road type. The fast growth experienced by this

    market explains the lesser impact on sales of the area sales potential and of competition.

  • 8/10/2019 Main Work Kk

    7/36

    Page 7of 36

    CHAPTER TWO

    2.0 DATA COLLECTION

    2.1 METHOD OF DATA COLLECTION

    The data collected is a raw or primary data. The data was collected by method of Registration.

    The statistics of sales are taken immediately they are made.

    2.2 DATA COLLECTED

    The products whose sales were considered in this research are:

    2.2.1 COCA COLA

    Coca-Cola is the most popular and biggest-selling soft drink in history. An icon of all times,

    Coca-Cola is the best-known product in the world.

    Created in Atlanta, Georgia, by Dr. John S. Pemberton, Coca-Cola was first offered as a fountain

    beverage by mixing Coca-Cola syrup with carbonated water. Coca-Cola was introduced in 1886,

    patented in 1887, registered as a trademark in 1893 and by 1895 it was being sold in every state

    and territory in the United States. In 1899, The Coca-Cola Company began franchised bottling

    operations in and outside the United States taking Coca-Cola to consumers in other parts of

    North America and Europe and in subsequent years to other parts of the world.

    In 1951, the refreshing wave of Coca-Cola arrived in Nigeria and has remained a hit with

    consumers across the country.

    Coca-Cola is available in: 35cl and 50cl classic glass contour bottle; 33cl on-the-go Can, 50cl

    and 1.5L PET bottle.

    Coca-cola is made with Carbonated water, sugar, Carbon-dioxide, caffeine, Phosphoric acid,

    caramel color and flavoring.

  • 8/10/2019 Main Work Kk

    8/36

    Page 8of 36

    2.2.2 FANTA

    Fanta is a bubbly, fruity, and colorful sparkling drink. The brand represents a playful spirit;

    appealing to everyone to laugh, play and take life less seriously.

    Launched in 1960, Fanta is the second oldest brand of The Coca-Cola Company in Nigeria.Fanta is enjoyed more than 130 million times everyday worldwide.

    In Nigeria, Fanta is available in orange and pineapple flavors.

    Fanta is available in: 35cl and 50cl glass bottle; 33cl on-the-go Can and 50cl PET bottle.

    Fanta is made of Carbonated water, sugar, citric acid, ascorbic acid, stabilizers, flavorings,

    sodium benzoate and colouring.

    2.2.3 SPRITE

    Sprite is the world's leading lemon-lime flavored soft drink. It is sold in more than 190 countries

    including Nigeria and ranks as the No. 4 soft drink worldwide. With a strong appeal to young

    people, Sprite is often perceived as the better for you Sparkling Beverage because of its clear

    color, caffeine-free, and naturally flavored formula.

    Packaged in the familiar green dimpled bottle with the shoulders, millions of people enjoy Sprite

    because of its crisp, clean taste that really quenches your thirst. Sprite also has an honest,

    straightforward attitude that sets it apart from other soft drinks and offers a total freedom from

    thirst.

    To appeal to its large youthful consumer base as well as bring out the creativity and ingenuity inthis group, Sprite has engaged in the Sprite Triple Slam activation. The Sprite Triple Slam is a

    property of the Sprite brand that combines three fun elements of basketball, music and dance..

    Sprite is available in: 35cl and 50cl glass bottle; 33cl on-the-go Can and 50cl PET bottle.

    Sprite is made of Carbonated water, sugar, citric acid, flavorings, sodium salt, and sodium

    benzoate.

    http://www.nigerianbottlingcompanyltd.com/Productsandbrands/Sparklingbeverages

    http://www.nigerianbottlingcompanyltd.com/Productsandbrands/Sparklingbeverageshttp://www.nigerianbottlingcompanyltd.com/Productsandbrands/Sparklingbeverageshttp://www.nigerianbottlingcompanyltd.com/Productsandbrands/Sparklingbeverages
  • 8/10/2019 Main Work Kk

    9/36

    Page 9of 36

    CHAPTER THREE

    3.0 DATA ANALYSIS

    3.1 Time Series

    3.1.1 Coke

    Year Variable (Coke) YEAR_ MONTH_ DATE_ Pred._Coke Forecast

    2001 3163820 2001 1 Jan-01

    2001 3163367 2001 2 Feb-01 3164555

    2001 3163453 2001 3 Mar-01 3164546

    2001 3164120 2001 4 Apr-01 3164711

    2001 3165928 2001 5 May-01 3165196

    2001 3165387 2001 6 Jun-01 3166426

    2001 3168931 2001 7 Jul-01 3166645

    2001 3168740 2001 8 Aug-01 3168782

    2001 3169621 2001 9 Sep-01 3169545

    2001 3169541 2001 10 Oct-01 3170452

    2001 3169897 2001 11 Nov-01 3170827

    2001 3170620 2001 12 Dec-01 3171236

    2002 3175360 2002 1 Jan-02 3171641

    2002 3177768 2002 2 Feb-02 3174468

    2002 3178135 2002 3 Mar-02 3176950

    2002 3176260 2002 4 Apr-02 3178275

    2002 3181135 2002 5 May-02 3177896

    2002 3180497 2002 6 Jun-02 3180558

    2002 3183760 2002 7 Jul-02 3181251

    2002 3187690 2002 8 Aug-02 3183479

    2002 3188532 2002 9 Sep-02 3186602

    2002 3188654 2002 10 Oct-02 31884172002 3185135 2002 11 Nov-02 3189368

    2002 3189708 2002 12 Dec-02 3187900

    2003 3193880 2003 1 Jan-03 3189749

    2003 3191497 2003 2 Feb-03 3192741

    2003 3196888 2003 3 Mar-03 3192676

    2003 3193135 2003 4 Apr-03 3195819

  • 8/10/2019 Main Work Kk

    10/36

    Page 10of 36

    2003 3193366 2003 5 May-03 3194987

    2003 3199897 2003 6 Jun-03 3194956

    2003 3195808 2003 7 Jul-03 3198579

    2003 3195497 2003 8 Aug-03 3197729

    2003 3198906 2003 9 Sep-03 31974092003 3197875 2003 10 Oct-03 3199181

    2003 3199497 2003 11 Nov-03 3199299

    2003 3201135 2003 12 Dec-03 3200346

    2004 3190357 2004 1 Jan-04 3201501

    2004 3199876 2004 2 Feb-04 3196005

    2004 3199535 2004 3 Mar-04 3199238

    2004 3200780 2004 4 Apr-04 3200080

    2004 3202551 2004 5 May-04 3201240

    2004 3203876 2004 6 Jun-04 3202751

    2004 3206686 2004 7 Jul-04 3204156

    2004 3206950 2004 8 Aug-04 3206364

    2004 3205551 2004 9 Sep-04 3207465

    2004 3205880 2004 10 Oct-04 3207245

    2004 3205135 2004 11 Nov-04 3207424

    2004 3204632 2004 12 Dec-04 3207093

    2005 3203865 2005 1 Jan-05 3206511

    2005 3200880 2005 2 Feb-05 3205849

    2005 3204689 2005 3 Mar-05 3203916

    2005 3204889 2005 4 Apr-05 3205266

    2005 3206807 2005 5 May-05 3205828

    2005 3208557 2005 6 Jun-05 3207185

    2005 3208805 2005 7 Jul-05 3208740

    2005 3207935 2005 8 Aug-05 3209569

    2005 3210651 2005 9 Sep-05 3209505

    2005 3212975 2005 10 Oct-05 3211059

    2005 3209555 2005 11 Nov-05 3212980

    2006 3209664 2005 12 Dec-05 3211915

    2006 3211888 2006 1 Jan-06 3211476

    2006 3211552 2006 2 Feb-06 3212513

    2006 3214880 2006 3 Mar-06 3212722

    2006 3213897 2006 4 Apr-06 3214720

    2006 3215135 2006 5 May-06 3214985

    2006 3215659 2006 6 Jun-06 3215890

  • 8/10/2019 Main Work Kk

    11/36

    Page 11of 36

    2006 3216680 2006 7 Jul-06 3216577

    2006 3211550 2006 8 Aug-06 3217476

    2006 3214897 2006 9 Sep-06 3215023

    2006 3215686 2006 10 Oct-06 3215994

    2006 3215875 2006 11 Nov-06 32167222006 3218551 2006 12 Dec-06 3217161

    2007 3226812 2007 1 Jan-07 3218680

    2007 3226543 2007 2 Feb-07 3223906

    2007 3226663 2007 3 Mar-07 3225886

    2007 3226098 2007 4 Apr-07 3226994

    2007 3227076 2007 5 May-07 3227251

    2007 3227387 2007 6 Jun-07 3227979

    2007 3228965 2007 7 Jul-07 3228474

    2007 3228987 2007 8 Aug-07 3229600

    2007 3228675 2007 9 Sep-07 3230097

    2007 3230543 2007 10 Oct-07 3230190

    2007 3232654 2007 11 Nov-07 3231314

    2007 3235645 2007 12 Dec-07 3232954

    2008 3237980 2008 1 Jan-08 3235132

    2008 3234790 2008 2 Feb-08 3237372

    2008 3230765 2008 3 Mar-08 3236597

    2008 3231843 2008 4 Apr-08 3234186

    2008 3235675 2008 5 May-08 3233842

    2008 3233489 2008 6 Jun-08 3235745

    2008 3232743 2008 7 Jul-08 3235258

    2008 3237611 2008 8 Aug-08 3234755

    2008 3239543 2008 9 Sep-08 3237275

    2008 3238563 2008 10 Oct-08 3239328

    2008 3238097 2008 11 Nov-08 3239714

    2008 3240231 2008 12 Dec-08 3239732

    2009 3242563 2009 1 Jan-09 3240777

    2009 3243795 2009 2 Feb-09 3242496

    2009 3241897 2009 3 Mar-09 3243918

    2009 3239780 2009 4 Apr-09 3243519

    2009 3237679 2009 5 May-09 3242278

    2009 3239670 2009 6 Jun-09 3240631

    2009 3240080 2009 7 Jul-09 3241056

    2009 3241780 2009 8 Aug-09 3241385

  • 8/10/2019 Main Work Kk

    12/36

    Page 12of 36

    2009 3240900 2009 9 Sep-09 3242487

    2009 3243650 2009 10 Oct-09 3242461

    2009 3243460 2009 11 Nov-09 3244054

    2009 3244674 2009 12 Dec-09 3244592

    2010 3238800 2010 1 Jan-10 32453722010 3237908 2010 2 Feb-10 3242445

    2010 3241765 2010 3 Mar-10 3240862

    2010 3242670 2010 4 Apr-10 3242279

    2010 3244000 2010 5 May-10 3243265

    2010 3246443 2010 6 Jun-10 3244464

    2010 3235330 2010 7 Jul-10 3246362

    2010 3240200 2010 8 Aug-10 3240992

    2010 3242587 2010 9 Sep-10 3241721

    2010 3243800 2010 10 Oct-10 3243116

    2010 3240180 2010 11 Nov-10 3244359

    2010 3244660 2010 12 Dec-10 3242911

    2011 3245856 2011 1 Jan-11 3244725

    2011 3248850 2011 2 Feb-11 3246047

    2011 3254640 2011 3 Mar-11 3248324

    2011 3252675 2011 4 Apr-11 3252526

    2011 3256800 2011 5 May-11 3253204

    2011 3251000 2011 6 Jun-11 3255992

    2011 3257540 2011 7 Jul-11 3253923

    2011 3259430 2011 8 Aug-11 3256912

    2011 3258440 2011 9 Sep-11 3259069

    2011 3261780 2011 10 Oct-11 3259506

    2011 3264550 2011 11 Nov-11 3261670

    2011 3266760 2011 12 Dec-11 3264110

    2012 3263760 2012 1 Jan-12 3266216

    2012 3268540 2012 2 Feb-12 3265500

    2012 3265769 2012 3 Mar-12 3268012

    2012 3270896 2012 4 Apr-12 3267446

    2012 3269123 2012 5 May-12 3270213

    2012 3266432 2012 6 Jun-12 3270310

    2012 3274436 2012 7 Jul-12 3268994

    2012 3272890 2012 8 Aug-12 3272975

    2012 3277006 2012 9 Sep-12 3273627

    2012 3278590 2012 10 Oct-12 3276370

  • 8/10/2019 Main Work Kk

    13/36

    Page 13of 36

    2012 3274360 2012 11 Nov-12 3278391

    2012 3280684 2012 12 Dec-12 3276975

    2013 Jan-13 3279010

    2013 Feb-13 3297889

    2013 Mar-13 3304216

    2013 Apr-13 3303210

    2103 May-13 3315400

    2013 Jun-13 3315650

    2013 Jul-13 3304235

    2013 Aug-13 3314872

    2013 Sep-13 3315785

    2013 Oct-13 3318460

    2013 Nov-13 3320078

    2013 Dec-13 3320050

  • 8/10/2019 Main Work Kk

    14/36

    Page 14of 36

    Autocorrelations

    Series: Coke

    Lag Autocorrelation Std. Errora Box-Ljung Statistic

    Value df Sig.b

    1 .968 .082 137.664 1 .000

    2 .941 .082 268.805 2 .000

    3 .912 .082 392.945 3 .000

    4 .883 .082 510.124 4 .000

    5 .858 .081 621.381 5 .000

    6 .829 .081 726.091 6 .000

    7 .805 .081 825.487 7 .000

    8 .780 .080 919.483 8 .000

    9 .753 .080 1007.873 9 .000

    10 .728 .080 1090.973 10 .000

    11 .701 .080 1168.586 11 .000

    12 .674 .079 1241.033 12 .000

    13 .649 .079 1308.614 13 .000

    14 .625 .079 1371.870 14 .000

    15 .601 .078 1430.809 15 .000

    16 .579 .078 1485.817 16 .000

    a. The underlying process assumed is independence (white noise).

    b. Based on the asymptotic chi-square approximation.

  • 8/10/2019 Main Work Kk

    15/36

    Page 15of 36

    Partial Autocorrelations

    Series: Coke

    Lag Partial Autocorrelation Std. Error

    1 .968 .083

    2 .075 .083

    3 -.040 .083

    4 -.027 .083

    5 .038 .083

    6 -.051 .083

    7 .044 .083

    8 -.014 .083

    9 -.038 .083

    10 -.010 .083

    11 -.028 .083

    12 -.012 .083

    13 .001 .083

    14 .020 .08315 -.024 .083

    16 .007 .083

  • 8/10/2019 Main Work Kk

    16/36

    Page 16of 36

    Model Description

    Model Type

    Model ID Coke Model_1 ARIMA(1,1,1)(0,0,0)

    Model Summary

    Fit Statistic Coke-Model_1

    Stationary R-squared 0.166

    R-squared 0.991

    RMSE 2873.385

    MAPE 0.0625

    MAE 2102.934

    MaxAPE 0.349

    MaxAE 11143.73

    Normalized BIC 16.065

    Statistics 13.068

    DF 16

    Sig. 0.668

  • 8/10/2019 Main Work Kk

    17/36

    Page 17of 36

  • 8/10/2019 Main Work Kk

    18/36

    Page 18of 36

    3.1.2 Fanta

    Year

    Variable

    (Fanta) YEAR_ MONTH_ DATE_ Pred._Fanta Forecast

    2001 3163135 2001 1 Jan-012001 3163420 2001 2 Feb-01 3163918

    2001 3163576 2001 3 Mar-01 3164323

    2001 3164345 2001 4 Apr-01 3164599

    2001 3164490 2001 5 May-01 3165249

    2001 3165686 2001 6 Jun-01 3165516

    2001 3167467 2001 7 Jul-01 3166443

    2001 3165476 2001 8 Aug-01 3167872

    2001 3168139 2001 9 Sep-01 3166871

    2001 3168432 2001 10 Oct-01 31686242001 3169453 2001 11 Nov-01 3169131

    2001 3169420 2001 12 Dec-01 3170039

    2002 3171131 2002 1 Jan-02 3170382

    2002 3174776 2002 2 Feb-02 3171720

    2002 3172709 2002 3 Mar-02 3174521

    2002 3173766 2002 4 Apr-02 3173773

    2002 3173135 2002 5 May-02 3174604

    2002 3172708 2002 6 Jun-02 3174372

    2002 3175765 2002 7 Jul-02 3174108

    2002 3175740 2002 8 Aug-02 3176141

    2002 3178135 2002 9 Sep-02 3176490

    2002 3179735 2002 10 Oct-02 3178326

    2002 3179689 2002 11 Nov-02 3179843

    2002 3185761 2002 12 Dec-02 3180267

    2003 3185576 2003 1 Jan-03 3184768

    2003 3187880 2003 2 Feb-03 3185618

    2003 3189135 2003 3 Mar-03 3187730

    2003 3189808 2003 4 Apr-03 3189200

    2003 3191646 2003 5 May-03 3190179

    2003 3190874 2003 6 Jun-03 3191819

    2003 3193821 2003 7 Jul-03 3191756

    2003 3193576 2003 8 Aug-03 3193927

    2003 3192850 2003 9 Sep-03 3194237

    2003 3195545 2003 10 Oct-03 3193985

  • 8/10/2019 Main Work Kk

    19/36

    Page 19of 36

    2003 3194556 2003 11 Nov-03 3195860

    2003 3196880 2003 12 Dec-03 3195557

    2004 3196881 2004 1 Jan-04 3197334

    2004 3194616 2004 2 Feb-04 3197717

    2004 3195821 2004 3 Mar-04 31963942004 3196477 2004 4 Apr-04 3197039

    2004 3198880 2004 5 May-04 3197534

    2004 3199135 2004 6 Jun-04 3199277

    2004 3199497 2004 7 Jul-04 3199821

    2004 3198800 2004 8 Aug-04 3200313

    2004 3196616 2004 9 Sep-04 3200024

    2004 3197397 2004 10 Oct-04 3198549

    2004 3199820 2004 11 Nov-04 3198794

    2004 3202487 2004 12 Dec-04 3200370

    2005 3204803 2005 1 Jan-05 3202565

    2005 3201835 2005 2 Feb-05 3204678

    2005 3200580 2005 3 Mar-05 3203271

    2005 3200386 2005 4 Apr-05 3202382

    2005 3201277 2005 5 May-05 3202059

    2005 3202770 2005 6 Jun-05 3202520

    2005 3202697 2005 7 Jul-05 3203560

    2005 3201806 2005 8 Aug-05 3203713

    2005 3205675 2005 9 Sep-05 3203210

    2005 3204635 2005 10 Oct-05 3205781

    2005 3205785 2005 11 Nov-05 3205536

    2006 3205907 2005 12 Dec-05 3206449

    2006 3206750 2006 1 Jan-06 3206865

    2006 3207900 2006 2 Feb-06 3207614

    2006 3207455 2006 3 Mar-06 3208604

    2006 3206487 2006 4 Apr-06 3208567

    2006 3203760 2006 5 May-06 3208000

    2006 3205880 2006 6 Jun-06 3206064

    2006 3208437 2006 7 Jul-06 3207096

    2006 3209110 2006 8 Aug-06 3208864

    2006 3209155 2006 9 Sep-06 3209667

    2006 3210227 2006 10 Oct-06 3209983

    2006 3210650 2006 11 Nov-06 3210879

    2006 3211875 2006 12 Dec-06 3211399

  • 8/10/2019 Main Work Kk

    20/36

    Page 20of 36

    2007 3216786 2007 1 Jan-07 3212531

    2007 3216453 2007 2 Feb-07 3216173

    2007 3216509 2007 3 Mar-07 3216759

    2007 3217378 2007 4 Apr-07 3217226

    2007 3219780 2007 5 May-07 32180712007 3219600 2007 6 Jun-07 3219962

    2007 3218480 2007 7 Jul-07 3220299

    2007 3217670 2007 8 Aug-07 3219777

    2007 3218650 2007 9 Sep-07 3219214

    2007 3219400 2007 10 Oct-07 3219761

    2007 3218450 2007 11 Nov-07 3220322

    2007 3219440 2007 12 Dec-07 3219797

    2008 3219352 2008 1 Jan-08 3220524

    2008 3221350 2008 2 Feb-08 3220588

    2008 3222210 2008 3 Mar-08 3222002

    2008 3220900 2008 4 Apr-08 3222875

    2008 3223780 2008 5 May-08 3222258

    2008 3219564 2008 6 Jun-08 3224202

    2008 3222807 2008 7 Jul-08 3221694

    2008 3222576 2008 8 Aug-08 3223554

    2008 3221786 2008 9 Sep-08 3223611

    2008 3220090 2008 10 Oct-08 3223162

    2008 3220800 2008 11 Nov-08 3221950

    2008 3219670 2008 12 Dec-08 3222170

    2009 3218560 2009 1 Jan-09 3221445

    2009 3220543 2009 2 Feb-09 3220530

    2009 3222890 2009 3 Mar-09 3221633

    2009 3232000 2009 4 Apr-09 3223338

    2009 3230760 2009 5 May-09 3229902

    2009 3231098 2009 6 Jun-09 3230459

    2009 3223000 2009 7 Jul-09 3231347

    2009 3229432 2009 8 Aug-09 3226261

    2009 3228450 2009 9 Sep-09 3229821

    2009 3234540 2009 10 Oct-09 3229506

    2009 3235567 2009 11 Nov-09 3233724

    2009 3231890 2009 12 Dec-09 3235257

    2010 3230700 2010 1 Jan-10 3233488

    2010 3232450 2010 2 Feb-10 3232591

  • 8/10/2019 Main Work Kk

    21/36

    Page 21of 36

    2010 3240060 2010 3 Mar-10 3233568

    2010 3236890 2010 4 Apr-10 3238843

    2010 3239098 2010 5 May-10 3237733

    2010 3237607 2010 6 Jun-10 3239431

    2010 3238555 2010 7 Jul-10 32388132010 3241606 2010 8 Aug-10 3239491

    2010 3243060 2010 9 Sep-10 3241704

    2010 3247380 2010 10 Oct-10 3243166

    2010 3248600 2010 11 Nov-10 3246569

    2010 3253437 2010 12 Dec-10 3248232

    2011 3251700 2011 1 Jan-11 3252281

    2011 3260807 2011 2 Feb-11 3252141

    2011 3263808 2011 3 Mar-11 3258720

    2011 3257354 2011 4 Apr-11 3262173

    2011 3261200 2011 5 May-11 3258999

    2011 3259860 2011 6 Jun-11 3261482

    2011 3254909 2011 7 Jul-11 3260989

    2011 3266010 2011 8 Aug-11 3257683

    2011 3264110 2011 9 Sep-11 3264621

    2011 3268065 2011 10 Oct-11 3264411

    2011 3255650 2011 11 Nov-11 3267485

    2011 3256120 2011 12 Dec-11 3259774

    2012 3260165 2012 1 Jan-12 3259008

    2012 3257760 2012 2 Feb-12 3261145

    2012 3259450 2012 3 Mar-12 3259668

    2012 3258895 2012 4 Apr-12 3260590

    2012 3264125 2012 5 May-12 3260292

    2012 3264560 2012 6 Jun-12 3263819

    2012 3263340 2012 7 Jul-12 3264775

    2012 3260320 2012 8 Aug-12 3264383

    2012 3262111 2012 9 Sep-12 3262420

    2012 3266560 2012 10 Oct-12 3263291

    2012 3269808 2012 11 Nov-12 3266341

    2012 3268900 2012 12 Dec-12 3269141

    2013 Jan-13 3269104

    2013 Feb-13 3278807

    2013 Mar-13 3269750

    2013 Apr-13 3270033

    2103 May-13 3269998

  • 8/10/2019 Main Work Kk

    22/36

    Page 22of 36

    2013 Jun-13 3272430

    2013 Jul-13 3273350

    2013 Aug-13 3273664

    2013 Sep-13 3269880

    2013 Oct-13 3271876

    2013 Nov-13 3273452

    2013 Dec-13 3276380

  • 8/10/2019 Main Work Kk

    23/36

    Page 23of 36

    Autocorrelations

    Series: Fanta

    Lag Autocorrelation Std. Errora Box-Ljung Statistic

    Value df Sig.b

    1 .972 .082 138.953 1 .000

    2 .946 .082 271.479 2 .000

    3 .921 .082 397.835 3 .000

    4 .898 .082 519.063 4 .000

    5 .877 .081 635.509 5 .000

    6 .853 .081 746.289 6 .000

    7 .828 .081 851.587 7 .000

    8 .801 .080 950.808 8 .000

    9 .778 .080 1045.094 9 .000

    10 .755 .080 1134.426 10 .000

    11 .732 .080 1219.034 11 .000

    12 .707 .079 1298.700 12 .000

    13 .685 .079 1373.977 13 .000

    14 .663 .079 1445.161 14 .000

    15 .636 .078 1511.041 15 .000

    16 .609 .078 1571.916 16 .000

    a. The underlying process assumed is independence (white noise).

    b. Based on the asymptotic chi-square approximation.

  • 8/10/2019 Main Work Kk

    24/36

    Page 24of 36

    Partial Autocorrelations

    Series: Fanta

    Lag Partial Autocorrelation Std. Error

    1 .972 .083

    2 .018 .083

    3 -.003 .083

    4 .051 .083

    5 .011 .083

    6 -.075 .083

    7 -.007 .083

    8 -.063 .083

    9 .051 .083

    10 -.021 .083

    11 -.004 .083

    12 -.033 .083

    13 .030 .083

    14 -.003 .083

    15 -.125 .083

    16 -.015 .083

  • 8/10/2019 Main Work Kk

    25/36

    Page 25of 36

    Model Description

    Model Type

    Model ID Fanta Model_1 ARIMA(1,1,1)(0,0,0)

    Model Summary

    Fit Statistic Fanta-Model_1

    Stationary R-squared 0.101

    R-squared 0.991

    RMSE 2776.094

    MAPE 0.059

    MAE 1896.053

    MaxAPE 0.367

    MaxAE 11956,841

    Normalized BIC 15.998

    Statistics 19.826

    DF 16

    Sig. 0.228

  • 8/10/2019 Main Work Kk

    26/36

    Page 26of 36

  • 8/10/2019 Main Work Kk

    27/36

    Page 27of 36

    3.1.3 Sprite

    Year

    Variable

    (Sprite) YEAR_ MONTH_ DATE_ Pred._Sprite Forecast

    2001 3162489 2001 1 Jan-01

    2001 3162463 2001 2 Feb-01 3163226

    2001 3164414 2001 3 Mar-01 3163565

    2001 3164935 2001 4 Apr-01 3164642

    2001 3164520 2001 5 May-01 3165507

    2001 3165429 2001 6 Jun-01 3165940

    2001 3165609 2001 7 Jul-01 3166521

    2001 3165486 2001 8 Aug-01 3166988

    2001 3165135 2001 9 Sep-01 3167268

    2001 3167420 2001 10 Oct-01 3167344

    2001 3168690 2001 11 Nov-01 3168118

    2001 3168410 2001 12 Dec-01 3169086

    2002 3170135 2002 1 Jan-02 3169612

    2002 3171760 2002 2 Feb-02 3170505

    2002 3170135 2002 3 Mar-02 3171652

    2002 3172755 2002 4 Apr-02 3171935

    2002 3173776 2002 5 May-02 3172925

    2002 3173656 2002 6 Jun-02 3173963

    2002 3174760 2002 7 Jul-02 3174639

    2002 3174497 2002 8 Aug-02 3175438

    2002 3175135 2002 9 Sep-02 3175912

    2002 3175709 2002 10 Oct-02 3176427

    2002 3176768 2002 11 Nov-02 3176969

    2002 3176737 2002 12 Dec-02 3177680

    2003 3179880 2003 1 Jan-03 3178110

    2003 3179135 2003 2 Feb-03 3179395

    2003 3182686 2003 3 Mar-03 3180080

    2003 3184576 2003 4 Apr-03 3181649

    2003 3184875 2003 5 May-03 3183366

    2003 3188497 2003 6 Jun-03 31846422003 3189840 2003 7 Jul-03 3186646

    2003 3187135 2003 8 Aug-03 3188480

    2003 3186860 2003 9 Sep-03 3188869

    2003 3189990 2003 10 Oct-03 3188987

    2003 3190764 2003 11 Nov-03 3190057

    2003 3190550 2003 12 Dec-03 3191081

  • 8/10/2019 Main Work Kk

    28/36

    Page 28of 36

    2004 3193135 2004 1 Jan-04 3191655

    2004 3193880 2004 2 Feb-04 3192853

    2004 3194865 2004 3 Mar-04 3193942

    2004 3193357 2004 4 Apr-04 3194995

    2004 3195684 2004 5 May-04 3195240

    2004 3195353 2004 6 Jun-04 3196113

    2004 3198831 2004 7 Jul-04 3196640

    2004 3196811 2004 8 Aug-04 3198090

    2004 3197445 2004 9 Sep-04 3198486

    2004 3199180 2004 10 Oct-04 3198912

    2004 3197657 2004 11 Nov-04 3199763

    2004 3195886 2004 12 Dec-04 3199884

    2005 3199980 2005 1 Jan-05 3199318

    2005 3198557 2005 2 Feb-05 3200208

    2005 3197878 2005 3 Mar-05 3200437

    2005 3199876 2005 4 Apr-05 3200348

    2005 3201229 2005 5 May-05 3200913

    2005 3202865 2005 6 Jun-05 3201763

    2005 3205357 2005 7 Jul-05 3202878

    2005 3205686 2005 8 Aug-05 3204446

    2005 3209880 2005 9 Sep-05 3205645

    2005 3206812 2005 10 Oct-05 3207781

    2005 3203357 2005 11 Nov-05 3208314

    2006 3204540 2005 12 Dec-05 3207512

    2006 3209660 2006 1 Jan-06 3207230

    2006 3205535 2006 2 Feb-06 3208697

    2006 3206780 2006 3 Mar-06 3208471

    2006 3207980 2006 4 Apr-06 3208635

    2006 3204586 2006 5 May-06 3209155

    2006 3204457 2006 6 Jun-06 3208453

    2006 3206340 2006 7 Jul-06 3207881

    2006 3206520 2006 8 Aug-06 3208102

    2006 3209125 2006 9 Sep-06 3208350

    2006 3210230 2006 10 Oct-06 3209349

    2006 3210447 2006 11 Nov-06 32104202006 3212886 2006 12 Dec-06 3211226

    2007 3216467 2007 1 Jan-07 3212485

    2007 3216456 2007 2 Feb-07 3214509

    2007 3216476 2007 3 Mar-07 3215925

    2007 3216990 2007 4 Apr-07 3216873

    2007 3216500 2007 5 May-07 3217669

  • 8/10/2019 Main Work Kk

    29/36

    Page 29of 36

    2007 3216443 2007 6 Jun-07 3218056

    2007 3216760 2007 7 Jul-07 3218288

    2007 3216550 2007 8 Aug-07 3218546

    2007 3216640 2007 9 Sep-07 3218662

    2007 3218490 2007 10 Oct-07 3218768

    2007 3218644 2007 11 Nov-07 3219432

    2007 3217456 2007 12 Dec-07 3219963

    2008 3218432 2008 1 Jan-08 3219889

    2008 3218670 2008 2 Feb-08 3220128

    2008 3219750 2008 3 Mar-08 3220387

    2008 3219550 2008 4 Apr-08 3220911

    2008 3220320 2008 5 May-08 3221222

    2008 3221564 2008 6 Jun-08 3221673

    2008 3220555 2008 7 Jul-08 3222387

    2008 3222342 2008 8 Aug-08 3222570

    2008 3224890 2008 9 Sep-08 3223242

    2008 3223780 2008 10 Oct-08 3224537

    2008 3226890 2008 11 Nov-08 3225101

    2008 3225765 2008 12 Dec-08 3226442

    2009 3224654 2009 1 Jan-09 3226985

    2009 3228650 2009 2 Feb-09 3226972

    2009 3228908 2009 3 Mar-09 3228213

    2009 3227098 2009 4 Apr-09 3229205

    2009 3229780 2009 5 May-09 3229297

    2009 3226564 2009 6 Jun-09 3230176

    2009 3229556 2009 7 Jul-09 3229799

    2009 3234654 2009 8 Aug-09 3230436

    2009 3233680 2009 9 Sep-09 3232542

    2009 3231675 2009 10 Oct-09 3233739

    2009 3229908 2009 11 Nov-09 3233879

    2009 3232009 2009 12 Dec-09 3233375

    2010 3230350 2010 1 Jan-10 3233617

    2010 3243800 2010 2 Feb-10 3233299

    2010 3231760 2010 3 Mar-10 3237325

    2010 3236000 2010 4 Apr-10 32364582010 3233900 2010 5 May-10 3236981

    2010 3229605 2010 6 Jun-10 3236755

    2010 3240125 2010 7 Jul-10 3235204

    2010 3233590 2010 8 Aug-10 3237429

    2010 3239760 2010 9 Sep-10 3237055

    2010 3241805 2010 10 Oct-10 3238632

  • 8/10/2019 Main Work Kk

    30/36

    Page 30of 36

    2010 3246660 2010 11 Nov-10 3240458

    2010 3241880 2010 12 Dec-10 3243255

    2011 3244990 2011 1 Jan-11 3243639

    2011 3252760 2011 2 Feb-11 3244783

    2011 3250800 2011 3 Mar-11 3248075

    2011 3249870 2011 4 Apr-11 3249800

    2011 3256230 2011 5 May-11 3250610

    2011 3259850 2011 6 Jun-11 3253149

    2011 3249350 2011 7 Jul-11 3256116

    2011 3255665 2011 8 Aug-11 3254830

    2011 3259065 2011 9 Sep-11 3255766

    2011 3266550 2011 10 Oct-11 3257602

    2011 3263530 2011 11 Nov-11 3261267

    2011 3254238 2011 12 Dec-11 3262898

    2012 3269786 2012 1 Jan-12 3260913

    2012 3255564 2012 2 Feb-12 3264339

    2012 3256768 2012 3 Mar-12 3262427

    2012 3267653 2012 4 Apr-12 3261250

    2012 3264115 2012 5 May-12 3263954

    2012 3267005 2012 6 Jun-12 3264855

    2012 3256740 2012 7 Jul-12 3266298

    2012 3256553 2012 8 Aug-12 3264063

    2012 3269120 2012 9 Sep-12 3262314

    2012 3270440 2012 10 Oct-12 3265143

    2012 3270559 2012 11 Nov-12 3267703

    2012 3272880 2012 12 Dec-12 3269468

    2013 Jan-13 3267386

    2013 Feb-13 3269665

    2013 Mar-13 3267989

    2013 Apr-13 3265996

    2103 May-13 3267035

    2013 Jun-13 3269123

    2013 Jul-13 3270541

    2013 Aug-13 3268790

    2013 Sep-13 32669852013 Oct-13 3269554

    2013 Nov-13 3270088

    2013 Dec-13 3274320

  • 8/10/2019 Main Work Kk

    31/36

  • 8/10/2019 Main Work Kk

    32/36

    Page 32of 36

    Partial Autocorrelations

    Series: Sprite

    Lag Partial Autocorrelation Std. Error

    1 .967 .083

    2 .109 .083

    3 .031 .083

    4 -.043 .083

    5 .107 .083

    6 -.045 .083

    7 -.045 .083

    8 -.055 .083

    9 -.066 .083

    10 .074 .083

    11 .063 .083

    12 -.156 .083

    13 .044 .083

    14 -.024 .083

    15 -.045 .083

    16 -.010 .083

  • 8/10/2019 Main Work Kk

    33/36

    Page 33of 36

    Model Description

    Model Type

    Model ID Sprite Model_1 ARIMA(1,1,1)(0,0,0)

    Model Summary

    Fit Statistic Sprite-Model_1

    Stationary R-squared 0.319

    R-squared 0.988

    RMSE 3310.33

    MAPE 0.072

    MAE 2334.801

    MaxAPE 0.324

    MaxAE 10500.563

    Normalized BIC 16.348

    Statistics 33.546

    DF 16Sig. 0.006

  • 8/10/2019 Main Work Kk

    34/36

    Page 34of 36

  • 8/10/2019 Main Work Kk

    35/36

    Page 35of 36

    3.2 Friedman Test

    Descriptive Statistics

    N Mean Std.

    Deviation

    Minimum Maximum Percentiles

    25th 50th (Median) 75th

    Coke 144 3220605.7431 29963.40051 3163367 3280684 3199620.25 3222324.5 3241867.75

    Fanta 144 3214567.6806 29374.61634 3163135 3269808 3195614.0 3214164.0 3234017.5

    Sprite 144 3213202.0139 29729.55225 3162463 3272880 3191356.75 3214664.5 3231946.75

    Ranks

    Mean Rank

    Coke 2.76Fanta 1.86

    Sprite 1.38

    Test Statisticsa

    N 144

    Chi-Square 140.292

    df 2

    Asymp. Sig. .000

    a. Friedman Test

    With an asymptotic significant value = .000 < .05the null hypothesis it reject for

    the alternate that the sales performance of the products is not equal. This is fatherly

    shown by the mean rank indicating that coke and sprite has the highest and least

    sales respectively with a mean rank range of 1.38

  • 8/10/2019 Main Work Kk

    36/36

    CHAPTER FOUR

    4.0 SUMMARY, CONCLUSION AND RECCOMMENDATION

    Nigeria Bottling Company (NBC) has been a major player in the production of soft

    drinks in Nigeria. The study focuses on the sales performance of her major

    products (Coke, Fanta and Sprite). In studying these variables, a raw data showing

    the sales rates of these products were collected from 20012012.

    The analysis was run using SPSS v21.0 with the aim modeling the sales of these

    products over the years and making forecast (2013).

    CONCLUSION

    Analysis showed that although with slight drops, there was a continuous increase

    in the sales of the products during the years in question. The model ARIMA (1,1,1)

    was developed for althrough for predicting the trend and forecasting subsequent

    years. The prediction almost followed the actual sales while the forecast showed

    there will be a increase in the sales of the product in 2013.

    Further test showed that the sales performances are not equal as the product coke

    led the way.

    RECOMMENDATION

    The rise shown in the forecast is not convincing and as such, the branch of NBC

    considered should improve in the stability of the sales of her product. Also, advert

    placement for both fanta and sprite should be considered to foster a health

    competition between the products.


Recommended